popups
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown content and a standard evaluation configuration file. It does not include any scripts, binary executables, or commands that would lead to unauthorized actions.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No network operations (curl, wget) or hardcoded credentials were found. The skill suggests reading a local marketing context file to provide better advice, which is a standard pattern for context-aware AI agents.
- [COMMAND_EXECUTION]: No shell commands or system calls are present in the skill files.
- [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to override the system prompt or bypass safety filters.
Audit Metadata